import math

empty_element = {
    "count" : 1,
    "p(x_i)" : 0,
    "I(x_i)" : 0
}

def read_text_file():
    path = '/Users/safak/Documents/UNI/IT/P1/text.txt'

    with open(path, 'r', encoding='utf-8') as file:
        content = file.read()
    return content

def Z_statistik():
    # Ergebnisse mit https://de.planetcalc.com/2476/ prüfbar
    message = read_text_file()

    m = len(message)

    elements = {}

    for char in message:
        if elements.__contains__(char):
            elements[char]["count"] += 1
        else:
            elements[char] = empty_element.copy()

    calculate(elements, m, message)

def Z2_statistik():
    message = read_text_file()

    m = len(message) - 1        # Letztes Zeichen kann kein Tupel mit "nichts" bilden

    elements = {}

    for i, char in enumerate(message):
        if i != m:
            tuple = char + message[i+1]
            if elements.__contains__(tuple):
                elements[tuple]["count"] += 1
            else:
                elements[tuple] = empty_element.copy()

    calculate(elements, m, message)

def W_statistik():
    message = read_text_file()

    m = 0
    i = 0

    elements = {}

    while i != len(message):
        word = ""

        if message[i].isalpha():
            # Fange ein Wort an
            word += message[i]

            # füge Zeichen hinzu bis Wortende erreicht ist
            while message[i+1].isalpha():
                i += 1
                word += message[i]

            # Erhöhe die Anzahl der Wörter in der Nachricht
            m += 1

            # Zähle die Häufigkeit der Wörter
            if elements.__contains__(word):
                elements[word]["count"] += 1
            else:
                elements[word] = empty_element.copy()

        # gehe weiter in der Nachricht
        i += 1

    calculate(elements, m, message)

def calculate(elements, m, message):
    for x_i in elements:
        elements[x_i]["p(x_i)"] = elements[x_i]["count"] / m
        elements[x_i]["I(x_i)"] = -1 * math.log2(elements[x_i]["p(x_i)"])

    h = 0
    for x_i in elements:
        h += elements[x_i]["p(x_i)"] * elements[x_i]["I(x_i)"]


    sorted_by_element = sorted(elements)

    sorted_by_count = dict(sorted(
                               elements.items(),
                               key = lambda item: item[1]["count"],
                               reverse=True
                               ))

    sorted_by_information = dict(sorted(
                                     elements.items(),
                                     key = lambda item: item[1]["I(x_i)"],
                                     reverse=True
                                     ))
    # Ausgabe
    for x_i in sorted_by_element:
        print(f"{elements[x_i]["count"]:3.0f} | {elements[x_i]["p(x_i)"]:10.7f} | {elements[x_i]["I(x_i)"]:10.7f} | »{x_i}«")
    print("Entropie der Nachricht = " + h.__str__() + "\n\n")

def main():
    Z_statistik()
    Z2_statistik()
    W_statistik()

if __name__ == '__main__':
    main()